Interaction History

Web browsing often appears ephemeral: users visit a few websites, complete a task, and move on. However, even short fragments of browsing activity can contain rich and structured behavioral signals. In this work, we conduct a comparative empirical study of two complementary behavioral inference tasks: session-level user identification and next-domain prediction. Both tasks are derived from the same cleaned event stream and evaluated on large-scale anonymous browsing traces, with sessionization and splitting adapted to the temporal requirements of each task. For user identification, we evaluate classical and neural models operating on session-level behavioral and domain features. For next-domain prediction, we combine graph-based modeling with Large Language Models (LLMs). Experimental results show that short browsing sessions are highly identifiable, while future navigation actions are highly predictable from long-term interaction structure combined with recent behavioral context. Furthermore, LLM-derived semantic features yield only marginal gains over purely structural and sequential models, indicating that repeated interaction patterns remain the dominant predictive signal in the evaluated web-browsing setup. These findings highlight the extent to which interaction history substantially contributes to both user identifiability and navigation predictability in browsing traces.

Large language models (LLMs) are increasingly deployed as personalized assistants that interact with users over extended periods of time. As conversations grow longer, relying on full interaction histories becomes increasingly inefficient and unreliable: long contexts introduce substantial computational overhead, making it difficult for models to consistently identify and utilize the most relevant information for the current request. These challenges have motivated memory systems that structure and retrieve user-specific information. In realistic interactions, users often seek practical guidance such as recommendations, planning, and decision support. Unlike factual recall tasks, personalized guidance requires models to integrate information across multiple past conversations and reason about changing user preferences and experiences. However, existing conversational memory evaluations mainly focus on retrieval and factual recall. To study this challenge, we introduce PRAGMA, a benchmark for evaluating personalized guidance in long-term conversations. PRGAMA contains curated longitudinal conversation histories, evidence annotations, and guidance scenarios grounded in evolving user contexts and incorrect user assumptions. Experiments across retrieval systems, memory systems, and long-context models reveal that current systems struggle both to recover the appropriate conversational evidence and to effectively use it for personalized guidance. Our results highlight the need for memory architectures that support robust conversational retrieval and memory-grounded reasoning beyond evidence recall.

In persistent interactions, long contexts may encode an evolving process rather than a fixed record: later events can revise or revoke earlier information, changing what remains valid and what conclusions follow. We call this setting information evolution (IE). Solving IE requires identifying valid records, applying updates in order, and reconstructing the query-relevant state from the event history. Existing text-first synthesis pipelines make such data difficult to verify because state transitions and answer logic remain implicit. We introduce EvolveScaler, a code-driven framework that defines information evolution before rendering it as natural language. Human-authored operational specifications define state transitions, record validity, difficulty controls, and executable answer logic; a strong LLM then synthesizes a self-contained simulator from each specification. Executing validated simulators produces natural-language multi-turn event histories, while deterministic replay computes reference answers and atomic checklists. We instantiate EvolveScaler with 117 task prototypes and 159 final-question operators across five difficulty levels spanning approximately 7 to 1,200 events per instance, yielding about 35,100 training examples and 585 validated evaluation instances. On the very_long tier, the strongest model reaches 59.3% avg@5, while six models score below 10%. Training an internal A3B model on 6,000 EvolveScaler examples improves performance over its base checkpoint on all eight independently constructed out-of-distribution benchmarks, with a 5.25-point average gain. These results show that code-driven IE synthesis provides both challenging evaluation and transferable training supervision.

As people increasingly interact with LLM assistants in daily life, continually adapting to individual preferences has become essential for effective long-term interactions. However, user preferences are rarely stated in full, and instead emerge through heterogeneous, latent, and noisy signals, with existing methods relying on raw interaction histories or costly reward-based optimization to manage personalization. We introduce HypReflect, a reliable, scalable framework for continual personalization that infers explicit, uncertainty-aware preference hypotheses from diverse user signals, reflectively refines them as new evidence accumulates, and incorporates the resulting user model through hypotheses-guided self-distillation. Experiments across three personalization settings: online personalization, multi-session interactions, and implicit behavioral signals, show that HypReflect outperforms a range of baselines, including raw-history and incremental-update methods. We further demonstrate strong generalization to unseen users and cross-domain settings, along with stability across context budgets, reusable hypotheses, and more focused personalization. These results suggest a step towards reliable and scalable continual personalization through explicit, revisable user preference hypotheses.

Long-horizon agents need a context manager to compress growing interaction histories into a bounded working context, via passive strategies or active strategies that decide how memory is accessed and reorganized. Meanwhile, prior optical-memory work mainly treats pixels as a dense codec for textualized histories, often presupposing that rendering context into optical memory incurs a significant performance drop relative to text, thus coupling this representation with SFT, self-distillation, or reinforcement learning to close this gap, leaving unresolved (i) how visual rendering performs as a context manager under a fair, controlled comparison, and (ii) whether this carrier offers a native advantage when history is inherently multimodal. In this paper, we formulate context management as a budget-constrained history transformation and introduce Visual Rendering (VR) as a representational context manager. Under a shared harness, policy model, trigger, and task domain, we evaluate VR on four text-centric and three multimodal benchmarks against four baselines (No Compression, Discard-All, Sliding Window, Summarization), finding visual memory is a natural carrier of native visual evidence. Building on this finding, we propose VERA (Visual Evidence-Retaining strategy for long-horizon Agents), a training-free context manager built on deterministic rendering with no exposed memory operations: on text-centric benchmarks it renders textual history as VR does, while on multimodal benchmarks it retains native visual observations instead of translating them into text. Across nearly all benchmarks, VERA cuts cumulative non-cache tokens by 31.5%-63.1% versus No Compression, matches existing managers on text-centric tasks, and achieves the highest accuracy among all baselines on multimodal tasks, supporting a modality-preserving view of long-horizon context management.

Large language model (LLM)-powered agents have rapidly evolved from code-completion tools into solvers of complex software engineering tasks. As developers collaborate with coding agents over time, their preferences emerge through repeated interactions and can be used to adapt agent behavior to better meet individual developers' needs. Capturing and reusing these preferences may reduce repeated corrections and improve developer-agent collaboration. Agent skills provide a lightweight mechanism for transferring experience without modifying model parameters. However, existing work primarily focuses on task-specific skills, and it remains unclear whether developer-specific skills distilled from interaction histories can generalize to future tasks. We propose a framework for extracting reusable developer preferences from interaction traces. It first generates personalized skills through rule-based bootstrapping and evidence-grounded refinement, and then evaluates them using a reproducible replay framework with an interactive, trajectory-conditioned LLM-based human developer simulator. We conduct an experiment on 206 real-world developer-agent sessions from 13 developers and compare personalized skills against no-skill, generic-skill, and other-user-skill baselines. Personalized skills provide small and inconsistent improvements over the no-skill baseline, whereas generic skills pooled across developers achieve the largest and most consistent gains. Further analysis suggests that personalized skills become more effective when developer preferences appear frequently, particularly when their histories contain multiple examples relevant to future tasks. These findings provide empirical insights into when developer-specific personalization is effective and demonstrate that broadly transferable procedural knowledge can be more robust than developer-specific preference signals.

Recent advances in generative recommendation (GR) leverage large language models (LLMs) as recommender backbones, enabling LLMs to directly generate recommendations conditioned on item-interaction histories. In these systems, items are often represented through semantic IDs (SIDs) added to the LLM vocabulary as special tokens. Ideally, SIDs imbue item token representations with semantic priors, thereby improving model generalization. However, standard vocabulary expansion typically initializes these tokens as random Gaussian vectors, discarding the SIDs' underlying continuous geometry and forcing the LLM to relearn token relationships from interaction data. To demonstrate the consequences of this design, we first show that training from this initialization tends to organize SID embeddings around item popularity rather than semantics. We further show that, despite partially reducing the reliance on popularity and improving cold item performance, the computationally expensive process of continual pretraining (CPT) fails to reliably recover the original semantic geometry. To address these findings, we propose a simple, parameter-free intervention that initializes SID token embeddings directly from their corresponding centroids in the semantic embedding space. Requiring only a few lines of code and no additional training or inference overhead, this drop-in approach improves pure-SFT Recall@5 by up to 16%, reaches peak performance with up to 40% fewer SFT steps, and improves cold-item Recall@5 by up to 60%. Moreover, on datasets that benefit from additional CPT, centroid initialization reaches comparable performance while requiring half as many CPT epochs. Together, our findings show that preserving SID geometry, beyond shared-prefix structure, provides a simple and effective semantic prior for LLM-based GR.

Existing personalized LLM benchmarks primarily rely on textual personas or isolated behavioral signals, providing limited evaluation of cross-domain behavioral personalization, where responses must be grounded in heterogeneous daily-life activities. To address this gap, we introduce LUNAR, the first benchmark for evaluating how LLMs personalize responses from longitudinal app interaction histories across universal daily-life domains, including clothing, food, housing, and mobility. To support scalable benchmark construction while mitigating data sparsity and privacy concerns, LUNAR uses a multi-stage coarse-to-fine synthesis pipeline grounded in real-world behavioral patterns. Fidelity analyses show closer alignment with real behavioral distributions than other synthetic benchmarks. Experiments on 19 mainstream LLMs show that access to behavioral logs is necessary but not sufficient for deep personalization: neither more context nor larger models guarantees better performance; effective personalization depends on selecting and integrating relevant evidence across domains. Direct retrieval of fine-grained behavioral records consistently outperforms compressed memory, while stronger personalization can come at the cost of privacy protection. These findings identify evidence selection, cross-domain integration, and privacy control as key challenges for personalized LLMs.

Large Language Models have enabled increasingly capable autonomous agents, yet personalization remains critical for making such agents practically useful. Recent benchmarks have begun evaluating personalization in agents, but they largely rely on static preference snapshots, fixed interaction logs, or question answering over predefined user profiles. Such designs fail to capture the complexity of evolving user preferences and neglect preference-conditioned task execution-a discrepancy we term as the knowledge-to-action gap. To address this challenge, we introduce IBA-Bench, a benchmark for implicit behavioral alignment constructed from longitudinal interaction histories that contain noise, implicit cues, and temporal inconsistencies. Unlike prior work, IBA-Bench evaluates whether an agent can execute tasks while satisfying implicit user constraints inferred from historical interactions. We further propose IBA-Agent, an agent framework that reconciles conflicting priorities through broad retrieval and trajectory-level alignment. Experiment results on IBA-Bench show that effective personalization remains a significant challenge for state-of-the-art LLM agents, and the proposed IBA-Agent substantially improves behavioral alignment in complex scenarios across nine application domains.

Long-term multimodal memory must support not only retrieving relevant information but also computing over observations accumulated across interactions. Existing systems largely emphasize \emph{retrieval memory}, organizing interaction histories through summaries and indexes to return query-relevant information at multiple granularities, from high-level abstractions to underlying records. In this paper, we formulate \emph{analytic memory} as a complementary abstraction that organizes recurring multimodal observations into queryable structures supporting filtering, aggregation, ranking, and temporal comparison. We present AdaMM, a framework that jointly supports retrieval and analytic memory. Rather than relying on application-defined schemas, AdaMM extracts provenance-linked attribute-value observations from dialogue, images, and contextual metadata, discovers recurring field structures, and materializes them for analytical access. At inference time, a memory-aware planner decomposes queries into retrieval and analytic operations and routes each operation to the appropriate tools. Experiments on two long-term multimodal memory benchmarks, MemEye and MemGallery, show that AdaMM improves performance by up to 11.3% and 6.9%, respectively.

We propose MEMOIR, a framework that segments user interaction histories into temporal windows, generates semantic behavioral memory for each period using an LLM, and aggregates current state, evolution direction, and predicted future into a single user representation. On the Electronics and Clothing_Shoes_and_Jewelry categories of Amazon Reviews 2023, MEMOIR is statistically tied with UniSRec, the strongest baseline, on aggregate NDCG@10 (0.0643 vs. 0.0641), splitting the four reported metrics 2-2: MEMOIR leads NDCG@10 and MRR, UniSRec leads HR@10 and HR@20. An ablation study finds that no single architectural component - the evolution-preserving contrastive loss, its directional-consistency term, or temporal window segmentation itself - individually explains much of MEMOIR's approximately 18% relative gain over ID-based SASRec; all four ablations land within 2% of the full model on aggregate NDCG@10. Stratifying test performance by a composite preference-drift score instead reveals where the gain concentrates: MEMOIR leads on ranking-quality metrics (NDCG@10, MRR) specifically among users at the high- and low-drift extremes of the distribution, while UniSRec leads the volume-oriented HR@10/HR@20 metrics across all drift strata and edges out MEMOIR on ranking quality in the middle band. We report this drift-stratified pattern, rather than the near-tied aggregate numbers or any single ablated component, as MEMOIR's most substantive and reproducible finding, and surface why it holds as an open question for future work.

Benchmarks for LLM-agent memory typically generate conversations first and extract answer keys afterwards -- with documented label-error and contamination problems -- and they overwhelmingly measure short interaction histories. We invert the pipeline: a seeded life-script sampler emits facts with validity intervals, volatility classes, and source channels before any text exists; an LLM renderer writes chat and email from per-event fact manifests; a fidelity verifier confirms every planted fact; and questions are instantiated mechanically from the script, so gold answers are script-valid by construction and separately validated for answerability. The synthetic, fictionalized corpus (~380 questions, 15 types) embeds features absent from the benchmarks we survey: per-fact validity intervals, sent/received trust distinctions, injection probes in a benign harness, and as-of-date question sets. Benchmarking five memory architectures against a no-memory control (fixed answerer, versioned LLM judge, three replicates, two horizons), we find backend rankings invert with history length: the budgeted curated-map memory that leads at three weeks loses recall of evicted content by nine weeks (96% to 72%) while a provenance-typed graph rises to 90%; the inversion is positive for all six users under complete cross-family re-judging (exact p=0.031). A full-rendered-history baseline ties or exceeds the best memory system at the short horizon but shows no judge-independent advantage at nine weeks, at about twice the read cost. Write-stage quality strongly correlates with downstream quality (weakly-written facts fail 24% vs 2%), and injection resistance tracked whether provenance boundaries survive representation. A layered architecture performs best among the memory systems in both regimes (96.8% short-horizon) and is released as Veracium, an open-source library, with the corpus generator and harness.

Real-world agent learning is often constrained by costly environment interactions, such as running time-consuming experiments or obtaining human feedback. In-context learning offers a highly sample-efficient way for agents to learn from their own interaction histories, but its gains disappear once that experience is removed from the context. Separately, context distillation provides a mechanism for internalizing contextual information into model weights. However, applying it to agents' interaction histories without sacrificing environment sample efficiency remains underexplored. We term this problem Experience Distillation and develop an implementation that requires no further environment interaction beyond the collected experience. Experiments on 749 curated software-engineering tasks and six text-adventure games show that it retains at least 64.8% of the gains from in-context learning across both domains, whereas direct supervised fine-tuning on the collected experience recovers only 3.8%. Compared with classical reinforcement-learning baselines, in-context learning from trial-and-error experience followed by Experience Distillation matches their performance with at least $9.6\times$ fewer environment samples.

AI Assistants are increasingly deployed in high-stakes settings, such as healthcare or government services. Yet their real-world behavior remains poorly understood due to strong context dependence. Current evaluation protocols follow a defense-in-depth paradigm with compounding layers of safeguards, ranging from traditional benchmarks to live or adversarial testing. Such benchmarks remain largely static and single-turn, limiting their ability to capture real-world variability in conversational settings. We propose StabilityBench, a principled, general and model-agnostic benchmark operator that transforms single-turn benchmark queries into multi-turn interaction histories. StabilityBench augments existing benchmarks by injecting realistic user simulations, through demographic proxies or sycophantic baits, while preserving original task intent. We apply StabilityBench to four benchmarks spanning mathematical reasoning, health question-answering and safety, and evaluate nine large language models under these conditions. Our results show that model performance is consistently unstable under these injections, with considerable performance degradations on three out of four benchmarks studied. These highlight important limitations of static evaluations and motivate more realistic evaluation settings. To this end, we propose StabilityBench-Mini: a size-preserving variant of StabilityBench that samples across diversification axes, enabling more realistic evaluation without increasing costs.

We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn interaction histories. Fully online OPD is costly because each update requires fresh student rollouts through the environment and teacher queries at visited histories. We propose Replayed-Prefix On-Policy Distillation (ReOPD), an off-environment alternative that reuses pre-collected teacher trajectories as replayed prefixes: the student acts at selected steps, while the teacher provides dense per-step supervision without executing new environment interactions. We show that multi-turn OPD introduces a prefix trap: making histories more student-on-policy improves relevance to the student, but can query the teacher on histories where its target is unreliable. This creates a two-sided distribution shift between student occupancy and teacher reliability. ReOPD addresses this by treating multi-turn OPD as a reliability-aware prefix distribution design and implements it with a simple step-decaying sampling schedule that emphasizes early, lower-shift prefixes. Across mathematical reasoning with Python and search environments over multiple teacher and student model scales, ReOPD preserves or improves OPD-level accuracy, uses zero tool calls during student training, and is at least 4$\times$ faster per rollout than OPD. ReOPD therefore turns expensive agent-environment interaction into a reusable offline resource, enabling scalable distillation across tools, tasks, and environments.

LLM-powered agents struggle with personalization when users issue raw, underspecified queries. In this setting, agents must infer latent intent, extract preferences from noisy interaction histories, and select among competing alternatives. Existing benchmarks rarely test this capability, as they often rely on user-refined queries or simplified histories. We introduce personalized product search (PPS), a testbed for agentic personalization under raw queries and diverse histories. We construct Agent Personalized Benchmark (APeB) from action logs, pairing underspecified intents with rich histories and user-viewed candidate items. Evaluating state-of-the-art LLMs with multi-step agent workflows, we find that models handle explicit queries well but struggle with early-stage queries requiring intent and preference discovery. Rubric analysis attributes this gap mainly to ineffective history use. A simple history-aware query-refinement pipeline, VQRA, yields consistent gains, highlighting the need for dedicated history-utilization modules in personalized agents.

How do two agents invent a shared language from scratch? In a Lewis signaling game, a sender and receiver must coordinate on a code using only their interaction history. We study five memory architectures across varying channel configurations with LLM agents and find that memory architecture matters more than channel capacity. Agents with a persistent private notebook benefit from surplus channel capacity and avoid the high-capacity collapse seen in stateless agents, achieving the most reliable coordination ($0.867 \pm 0.023$ at capacity = 25). Stateless agents peak at moderate capacity and then degrade as the vocabulary grows beyond what a rolling context window can track The notebook externalizes learned conventions, freeing agents from having to re-derive codes each round. An information bottleneck-inspired argument predicts an optimal capacity equal to the number of objects. Instead, the bottleneck (capacity = 8) proves to be a fragility point, and surplus capacity is generally better. We show that channel capacity alone cannot predict coordination; memory architecture determines whether agents turn interaction history into stable conventions, and both dimensions are needed to understand how signals become language.

World models in partially observed environments rely on latent representations that summarize interaction history, but in many modern LLM-based architectures predictive performance fails to reflect representation quality due to history bypass, rendering the latent state unidentifiable. Strict latent state mediation, requiring predictions to depend only on the latent state and action, is a classical principle that resolves this, but enforcing it in text-based settings is an open challenge: textual latent states are discrete and non-differentiable, precluding variational training, and expressive LLM decoders readily ignore the bottleneck. We show how to make strict mediation work in the text domain. We formalize why it is necessary, showing that strict mediation makes representation quality empirically testable while history-leaky architectures break this connection. We then introduce textual latent states, which are discrete, interpretable, and variable-length, and factorized GRPO (fGRPO), a tree-structured reinforcement learning method that enforces strict mediation during training. Experiments on TextWorld and ScienceWorld show preserved one-step prediction accuracy alongside up to 57% gains in representation quality and 98% improvements in rollout performance, increasing with task complexity and horizon.

Sequential user behavior modeling is widely adopted in industrial recommender systems; however, significant gaps remain in financial services, where pre-login web interactions and authenticated in-app experiences differ drastically. Specifically, pre-login web users typically explore new products, whereas logged-in app users focus on account servicing. Due to the challenge of cross-channel entity resolution (e.g., matching anonymous web sessions to authenticated mobile accounts), web-based intent signals remain underutilized for post-authentication personalization. Existing methods for capturing web-based intent are often ad-hoc and narrow, lacking the flexibility to support both quantitative downstream recommendations and qualitative understanding at scale. In this work, we propose a scalable and dual-purpose intent prediction framework for web-based interactions and demonstrate its applicability for personalization. Our approach transforms raw web clickstreams into two outputs: a self-supervised Transformer encodes multi-modal clickstreams into a compact session embedding, while an LLM-based taxonomy generation and distillation pipeline produces interpretable intent labels. Our system demonstrates that self-supervised clickstream representations combined with LLM-distilled taxonomies can jointly serve quantitative tasks and qualitative understanding in production: on the mobile homepage tile ranking task, the session embedding improves macro Recall@1 by 1.88% and reduces Log Loss by 13.38% over production baselines. On the user conversion prediction task, the embedding outperforms the LLM labels by 4.3% on micro F1, while the distillation layer delivers interpretable labels at ultra-low latency with only a 7% performance drop.

Large-scale learner-task interaction data are crucial for intelligent educational systems but are costly to collect and constrained by privacy and learner engagement. Learner simulators play a critical role in simulating scalable learner behavior without the need for continuous involvement of real learners. However, existing methods are predominantly \textbf{individual-centric}, pairing a simulator with each learner to iteratively infer latent knowledge states from dense interaction histories, which is both data- and computation-intensive, and fragile in cold-start scenarios. We propose a \textbf{cohort-aware roll-call simulation paradigm} that first constructs cohort-level proficiency priors and refines individual learner states through a small number of targeted diagnostic queries. Based on this paradigm, we introduce \textbf{Edu-Theater}, an LLM-powered agent system that performs cohort-aware learner simulation via a teacher agent and retrospective roll-call probing over learner logs. Edu-Theater enables scalable future behavior simulation without the need for dense per-learner histories. Experiments on two real-world datasets demonstrate that Edu-Theater achieves higher simulation accuracy with significantly fewer LLM calls, producing synthetic data that enhances downstream applications such as adaptive testing.

Repeated reference games test whether interlocutors replace their initially long descriptions with shorter, partner-specific conventions grounded in shared interaction history. Prior work shows that multimodal LLMs fail to become more efficient across rounds, although they align on the labels they use. How can we determine whether this alignment reflects partner-specific grounding rather than a shared task vocabulary? We address this question by comparing capable multimodal agent dyads with human dyads from the KTH Tangrams corpus. Our novel methodological contribution is a constrained pseudo-dyad baseline that matches the original referential task structure, but breaks partner history. This baseline enables us to test whether the observed label alignment depends on interaction with a specific partner. Across three analytic layers (task competence, description strategy, alignment dynamics), we find clear differences. Humans reduce effort through entrainment, compressing descriptions and increasing label alignment with partners. Agents instead maintain fixed effort levels, producing verbose descriptions from round one, with near-ceiling label overlap that is statistically indistinguishable between real and pseudo dyads. MLLMs thus achieve coordination without convention, succeeding by verbose description rather than by forming the compact, history-dependent referring expressions characteristic of human dialogue.

LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale requires agents to persistently store, retrieve, and update their own memory across sessions. A rich ecosystem of agent memory systems has emerged spanning flat retrieval, LLM-mediated extraction, consolidating fact stores, and agentic control flows. Yet, their system-level behavior remains uncharacterized. We present the first systems characterization of agent memory. First, we introduce a system-oriented taxonomy classifying agent memory systems along four axes. Second, we build a phase-aware profiling harness attributing cost to construction, retrieval, and generation. Third, we characterize ten representative systems across two benchmark suites, uncovering how design choices shift cost across the write and read paths. Finally, we derive 10 system recommendations covering construction scheduling, capability floors, amortization via query volume, freshness-latency tradeoffs, and fleet-scale management.

Despite recent progress, LLM agents still struggle with reasoning over long interaction histories. While current memory-augmented agents rely on a static retrieve-then-reason paradigm, this rigid pipeline design prevents them from dynamically adapting memory access to intermediate evidence discovered during inference. To bridge this gap, we propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism. We represent memory as a Cue-Tag-Content graph, where associative tags serve as semantic bridges connecting fine-grained cues to memory contents. Operating on this structure, our active reconstruction mechanism integrates LLM reasoning directly into memory access, allowing the agent to iteratively explore and prune retrieval paths based on accumulated evidence. This ensures that memory retrieval is dynamically adapted to the reasoning context while avoiding combinatorial explosion caused by unconstrained expansion. Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines (up to 23%), while substantially reducing token and runtime cost, highlighting the effectiveness of active and associative reconstruction for long-horizon memory reasoning.

Long-context reasoning requires models to access, retrieve, and integrate evidence scattered across documents, dialogues, and accumulated interaction histories. Standard retrieval-augmented generation reduces this problem to top-$K$ chunk retrieval, but such passive access can discard relevant evidence before reasoning begins, especially when relevance depends on broader context. We propose HMARS, a hierarchical multi-agent memory system that treats long contexts as managed memory rather than a flat retrieval corpus. Sub-agents maintain grounded access to bounded memory regions, mid-agents manage regional context and provide query-specific coordination, and a frontier model performs final reasoning over retrieved evidence pages. To evaluate this view, we construct two diagnostic benchmarks targeting evidence breadth and context-dependent relevance. Across long-document and multi-turn memory tasks, HMARS achieves the best overall performance against retrieval, reranking, full-context, graph-based, and agentic long-context baselines. Evidence coverage analysis further shows that its gains come from retrieving the required supporting evidence more completely, rather than merely changing the final answer prompt.

Long-context dialogue systems must decide both when to access memory and which parts of the interaction history are relevant. Existing approaches typically rely on heuristic retrieval signals or always-on memory usage, failing to account for the changing and potentially inconsistent nature of user preferences. In this work, we propose a unified framework for memory access and selection based on changing preferences. We formulate personalized memory retrieval as identifying which historical turns provide evidence about a user's latent preference state, rather than relying on surface-level semantic similarity. To this end, we quantify the utility of each memory turn using a Bayes factor, defined as the improvement in the model's likelihood of the reference response when the turn is included in context. This provides a principled measure of evidence strength and a unified signal for both memory access and selection. By framing memory retrieval as utility estimation, the model learns to identify salient turns and regulate memory usage based on expected utility. Experiments on four heterogeneous memory benchmarks show that our approach outperforms existing embedding-based retrieval on long-context, preference-intensive tasks where modeling changing preferences is essential, while remaining competitive in low-density regimes where semantic similarity suffices.

Many decision-support settings require systems that adapt to individual users, but evaluation data for this problem remain limited. Existing benchmarks for user understanding often rely on simulated users or model-generated behavior, even though recent work cautions that model-based simulations can diverge systematically from human behavior. We introduce \textsc{BehaviorBench}, a benchmark for evaluating personalized decision modeling from real-world behavioral traces. \textsc{BehaviorBench} reconstructs wallet-level decision histories from observed public prediction-market and on-chain records, and organizes them into two complementary task layers: \emph{Belief prediction}, which predicts a user's final revealed stance and confidence in a market, and \emph{Trade prediction}, which predicts the direction and amount of individual transactions. Across 2,000 evaluation wallets, the benchmark contains 141,445 Belief instances and 1,485,972 Trade instances, with disjoint support pools for retrieval-based evaluation. We evaluate frontier and open-weight generative models under four history interfaces: no personalization, direct recent history, generated user profiles, and retrieved support-wallet evidence. Personalization improves Belief prediction more consistently than Trade prediction, model rankings change across task layers and metrics, and different history interfaces expose different failure modes. \textsc{BehaviorBench} provides an evaluation setting for studying whether personalized methods can use real-world behavioral evidence rather than simulated users alone.

Large language models (LLMs) have evolved into interactive agents that collaborate with users in real-world tasks. Effective collaboration in such settings increasingly depends on understanding the user beyond what is explicitly stated, as user intent is often reflected in fragmented daily interactions and requires both personalized modeling and proactive interaction. However, existing agent benchmarks primarily evaluate reasoning and tool use, largely overlooking the challenges of inferring and leveraging user preferences in realistic scenarios. To address this gap, we introduce VitaBench 2.0, a benchmark for evaluating personalized and proactive agent behavior in long-term user interactions. In VitaBench 2.0, tasks are organized as temporally ordered sequences for individual users, where preferences are embedded in fragmented and heterogeneous interactions. Successful completion of tasks requires the agent to continuously extract, utilize, and update user preferences from these interactions. We further evaluate proactiveness through tasks that require agents to recognize missing information and actively acquire it from users or environments before making decisions. To support systematic analysis, we provide an extensible memory interface that enables controlled comparison across different memory architectures. We benchmark a diverse set of frontier proprietary and open-source LLMs. Results show that real-world personalization remains highly challenging even for state-of-the-art models, revealing a substantial gap between current capabilities and practical requirements. Extensive analysis further reveals the failure modes and capability bottlenecks of current agents in real-world personalized decision-making, providing insights for future model improvements.

Existing large language model (LLM) based memory systems apply universal, static policies that overlook a fundamental reality: the contexts that are worth storing in memory are different across users. This misalignment wastes limited memory budget on transient interactions while failing to preserve critical context for long horizon tasks. To address this gap, we investigate an underexplored question: can LLM based memory systems learn personalized memory policies? We introduce PerMemBench, the first benchmark for evaluating personalized memory systems, featuring multi year, multi domain interaction histories across diverse user personas. We further present the first empirical study of memory personalization, proposing session level storage gating, a lightweight framework that selectively bypasses memory operations for transient sessions. Our study confirms that personalization yields substantial retention gains under perfect gating, yet reveals that accurate gating remains an open and critical challenge.

Long-horizon agentic reasoning requires large language models to act over long interaction histories containing thoughts, tool calls, observations, and partial conclusions. The challenge is not merely that these histories grow long, but that information needed for the current decision may be scattered across distant steps and only become relevant later. Existing approaches address this difficulty by truncating the interaction history, compressing it into shorter surrogates, or retrieving selected parts of it for reuse, but they do not explicitly model how access to past interaction should adapt to the agent's evolving state. We instead cast long-horizon reasoning as a problem of state-adaptive memory. To this end, we propose State-Adaptive Memory~(SAM), a standalone framework that consolidates ongoing interaction into compact memory cues while preserving raw trajectory pages for intent-driven recall. These cues are not treated as replacements for history; rather, they serve as lightweight handles that allow the agent to reconstruct temporally distant information according to its current needs, without retraining the underlying backbone. We further optimize the memory module through expert-guided supervision and reinforcement learning, aligning it with trajectory-level utility. Across BrowseComp, BrowseComp-ZH, WideSearch, and HLE, SAM consistently outperforms strong baselines over diverse agent backbones. Our results suggest that explicit memory modeling provides a simple and effective foundation for long-horizon agentic reasoning.

Robotic assistants in long-term human-robot collaboration need to assist users under partial observations while leveraging cross-day interaction history. However, human traits and routines are often unknown at the beginning of collaboration, making passive infer-then-act assistance ineffective and inefficient. To address this challenge, we study a cross-day proactive asking setting for continual task assistance and propose PACT (Proactive Asking for Continual Task Assistance), an ask-or-act framework that determines whether clarification should be sought before taking action. PACT leverages current observations together with accumulated interaction history to evaluate contextual sufficiency, enabling the robot to provide more reliable assistance and progressively adapt to the user over time. We implement its primary learned instantiation using reinforcement learning and evaluate alternative instantiations under the same framework. To assess such behavior, we further introduce a clarification utility metric that quantifies the trade-off between assistance accuracy and the frequency of clarification requests. Experiments in multi-day embodied collaboration scenarios demonstrate that, compared with passive inference baselines, PACT consistently improves both assistance accuracy and clarification utility, highlighting the importance of proactive asking in continual human-robot collaboration.

Experience-driven learning has emerged as a promising paradigm for enabling agents to improve from interaction trajectories by accumulating and reusing past experience. However, existing approaches are predominantly developed in textual settings and rely on manually designed memory schemas, limiting their applicability to multimodal environments. In real-world scenarios, experience is inherently multimodal, involving heterogeneous signals across perception, reasoning, and action, which makes effective memory design significantly more challenging. In particular, the optimal way to structure and utilize multimodal experience is highly task-dependent and evolves over time, rendering fixed memory designs insufficient. In this work, we propose a new paradigm, learning to learn from multimodal experience, which shifts memory design from a predefined component to an adaptive and learnable process. Our framework enables agents to dynamically construct, organize, and utilize memory based on task requirements and interaction history, effectively learning how to structure experience for improved performance. Experiments demonstrate that adaptive memory design substantially enhances agent performance and generalization across multimodal tasks, highlighting the critical role of learning memory mechanisms in experience-driven learning.

Long-horizon personalization requires dialogue assistants to retrieve user-specific facts from extended interaction histories. In practice, many relevant facts often have low semanticsimilarity to the query under dense retrieval. Standard Retrieval-Augmented Generation (RAG) and GraphRAG systems are still largely retrospective: they rely on embedding similarity to the query or on fixed graph traversals, so they often miss facts that matter for the user's needs but lie far from the query in embedding space. Inspired by prospection, the human ability to use imagined futures as cues for recall, we introduce Prospection-Guided Retrieval (PGR), which decouples retrieval from how memories are stored. Given a user query, PGR first expands the goal into a short Tree-of-Thought (ToT) or linear chain of plausible next steps, and uses these steps as retrieval probes rather than relying on the original query alone. The facts retrieved by these probes are then used to personalize the next round of prospection, enabling PGR to uncover additional memories that become relevant only after the simulation is grounded in the user's history. We also introduce MemoryQuest, a challenging multi-session benchmark in which each query is annotated with 3--5 dated reference facts subject to a low query-reference similarity constraint. Across 1,625 queries spanning 185 user profiles from 3 publicly available datasets, PGR-TOT substantially improves retrieval, including nearly 3x recall on MemoryQuest over the strongest baseline. In pairwise LLM-as-judge comparisons against baselines, PGR-generated responses are preferred on 89--98% of queries, with blinded human annotations on held-out subsets showing the same trend. Overall, the results demonstrate that explicit prospection yields large gains in long-horizon retrieval and response quality relative to similarity-only baselines.

Task completion in digital and physical environments increasingly involves complex temporal interaction, where actions and observations unfold over different time scales rather than align with fixed observation--action steps. To model such interactions, we propose \emph{Engagement Process} (EP), an interaction formalism that inherits the decision-theoretic structure of POMDPs while making time explicit in the action--observation interface. EP represents actions and observations as decoupled event streams along time, rather than updates paired at fixed decision steps. This interface captures single-agent timing issues such as deliberation latency, delayed feedback, and persistent actions, while supporting richer agent-side organization, multi-rate coordination, and compositional interaction among subsystems. Across toy, LLM-agent, and learning experiments, EP exposes temporal behaviors hidden by step-based interfaces and enables policies to adapt under explicit time costs.

Personalized user understanding from large-scale digital traces remains a fundamental challenge. Traditional user profiling methods rely on discriminative models and manual feature engineering to predict discrete attributes, often producing fragmented and logically inconsistent profiles that generalize poorly to long-tail behaviors. In this work, we study a generative paradigm in which large language models (LLMs) summarize long and noisy behavioral histories into coherent narratives that capture nuanced user evolution. Our experiments show that even strong LLMs remain limited in complex and implicit personalization reasoning. We propose UserGPT, a framework for improving LLM-based persona understanding through both attribute generation and summary generation. To address the scarcity of real-world behavioral data, we develop a User Behavior Simulation Engine that produces realistic and complex user trajectories. We further introduce a Data-Centric Semantization module that transforms heterogeneous behavioral logs into structured and semantically coherent inputs, reducing noise and sparsity. On top of this pipeline, we design a curriculum-driven post-training strategy that combines multi-stage Supervised Fine-Tuning (SFT) with Dual-Filter Group Relative Policy Optimization (DF-GRPO) to strengthen reasoning over long behavioral histories. We also construct HPR-Bench, a benchmark for holistic persona reasoning derived from simulated data. On HPR-Bench, UserGPT achieves an Avg@10 score of 0.7325 on tag prediction and an $Acc_{Ex}$ score of 0.7528 on summary generation, while compressing behavioral records by up to 97.9% with critical information preserved. These results demonstrate the effectiveness of UserGPT for holistic persona reasoning and personalized user-agent interaction.

Modern Deep Learning Recommendation Models (DLRMs) follow scaling laws with sequence length, driving the frontier toward ultra-long User Interaction History (UIH). However, the industry-standard "Fat Row" paradigm, which pre-materializes these sequences into every training example, creates a storage and I/O wall where data infrastructure usage exceeds GPU training capacity due to data redundancy that is amplified in multi-tenant environments where models with vastly different sequence length requirements share a union dataset. We present a \emph{versioned late materialization} paradigm that eliminates this redundancy by storing UIH once in a normalized, immutable tier and reconstructing sequences just-in-time during training via lightweight versioned pointers. The system ensures Online-to-Offline (O2O) consistency through a bifurcated protocol that prevents future leakage across both streaming and batch training, while a read-optimized immutable storage layer provides multi-dimensional projection pushdown for heterogeneous model tenants. Disaggregated data preprocessing with pipelined I/O prefetching and data-affinity optimizations masks the latency of training-time sequence reconstruction, keeping training throughput compute-bound by GPUs. Deployed on production DLRMs, the system reduces training data infrastructure resource usage while enabling aggressive sequence length scaling that delivers significant model quality gains, serving as the foundational data infrastructure for modern recommendation model architectures, including HSTU and ULTRA-HSTU.

Egocentric assistants often rely on first-person view data to capture user behavior and context for personalized services. Since different users exhibit distinct habits, preferences, and routines, such personalization is essential for truly effective assistance. However, effectively integrating long-term user data for personalization remains a key challenge. To address this, we introduce EgoSelf, a system that includes a graph-based interaction memory constructed from past observations and a dedicated learning task for personalization. The memory captures temporal and semantic relationships among interaction events and entities, from which user-specific profiles are derived. The personalized learning task is formulated as a prediction problem where the model predicts possible future interactions from individual user's historical behavior recorded in the graph. Extensive experiments demonstrate the effectiveness of EgoSelf as a personalized egocentric assistant. Code is available at https://abie-e.github.io/EgoSelf/.

Desktop interaction streams provide a continuous, privacy-sensitive record of interleaved user tasks. Transforming these streams into task-organized personal logs on-device faces two main challenges: exhaustive Vision-Language Model (VLM) processing strains local resources, and global stream processing causes cross-task context pollution. We present FOCAL (Filtered On-device Continuous Activity Logging), a privacy-first multi-agent system utilizing a unified filter-plan-log architecture. It cascades a lightweight Filter Agent for noise suppression, a text-only Brain Agent for task attribution, a Record Agent for selective visual reasoning, and a task-isolated Memory Agent for context-coherent summarization. Experiments on DesktopBench (comprising 2,572 screenshots across 420 complex sessions) show FOCAL reduces total token consumption by 60.4% and VLM call count by 72.3% versus a baseline, while boosting Key Information Recall (KIR) from 0.38 to 0.61. Crucially, under $A{\to}B{\to}A$ task interruptions, FOCAL maintains Task Acc 0.81 and KIR 0.80, whereas the baseline collapses to Task Acc 0.03. FOCAL pioneers the efficient, on-device summarization of instruction-free desktop streams into multi-perspective personal logs.

User preferences evolve across months of interaction, and tracking them requires inferring when a stated preference has been changed by a subsequent life event. We define this problem as long-horizon personalization and observe that progress on it is limited by data availability and measurement, with no existing resource providing both naturalistic long-horizon interactions and the ground-truth provenance needed to diagnose why models fail. We introduce a data generator that produces conversations from a structured mental state graph, yielding ground-truth provenance for every preference change across 6-month timelines, and from it construct HorizonBench, a benchmark of 4,245 items from 360 simulated users with 6-month conversation histories averaging ~4,300 turns and ~163K tokens. HorizonBench provides a testbed for long-context modeling, memory-augmented architectures, theory-of-mind reasoning, and user modeling. Across 25 frontier models, the best model reaches 52.8% and most score at or below the 20% chance baseline. When these models err on evolved preferences, over a third of the time they select the user's originally stated value without tracking the updated user state. This belief-update failure persists across context lengths and expression explicitness levels, identifying state-tracking capability as the primary bottleneck for long-horizon personalization.

User behavior in the real world is diverse, cross-domain, and spans long time horizons. Existing user modeling benchmarks however remain narrow, focusing mainly on short sessions and next-item prediction within a single domain. Such limitations hinder progress toward robust and generalizable user models. We present HORIZON, a new benchmark that reformulates user modeling along three axes i.e. dataset, task, and evaluation. Built from a large-scale, cross-domain reformulation of Amazon Reviews, HORIZON covers 54M users and 35M items, enabling both pretraining and realistic evaluation of models in heterogeneous environments. Unlike prior benchmarks, it challenges models to generalize across domains, users, and time, moving beyond standard missing-positive prediction in the same domain. We propose new tasks and evaluation setups that better reflect real-world deployment scenarios. These include temporal generalization, sequence-length variation, and modeling unseen users, with metrics designed to assess general user behavior understanding rather than isolated next-item prediction. We benchmark popular sequential recommendation architectures alongside LLM-based baselines that leverage long-term interaction histories. Our results highlight the gap between current methods and the demands of real-world user modeling, while establishing HORIZON as a foundation for research on temporally robust, cross-domain, and general-purpose user models.

Effective user modeling requires distinguishing between short-term and long-term preference evolution. While item embeddings have become a key component of recommender systems, standard approaches like Item2Vec treat user histories as unordered sets (bag-of-items), implicitly assuming that interactions separated by minutes are as semantically related as those separated by months. This simplification flattens the rich temporal structure of user behavior, obscuring the distinction between coherent consumption sessions and gradual interest drifts. In this work, we introduce TAI2Vec (Time-Aware Item-to-Vector), a family of lightweight embedding models that integrates temporal proximity directly into the representation learning process. Unlike approaches that apply global time constraints, TAI2Vec is user-adaptive, tailoring its temporal definitions to individual interaction paces. We propose two complementary strategies: TAI2Vec-Disc, which utilizes personalized anomaly detection to dynamically segment interactions into semantic sessions, and TAI2Vec-Cont, which employs continuous, user-specific decay functions to weigh item relationships based on their relative temporal distance. Experimental results across eight diverse datasets demonstrate that TAI2Vec consistently produces more accurate and behaviorally grounded representations than static baselines, achieving competitive or superior performance in over 80% of the datasets, with improvements of up to 135%. The source code is publicly available at https://github.com/UFSCar-LaSID/tai2vec.

Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints. While summarizing history via interest centers offers a practical alternative, existing methods struggle to (1) identify user-specific centers at appropriate granularity and (2) accurately assign behaviors, leading to quantization errors and loss of long-tail preferences. To alleviate these issues, we propose Hierarchical Sparse Activation Compression (HiSAC), an efficient framework for personalized sequence modeling. HiSAC encodes interactions into multi-level semantic IDs and constructs a global hierarchical codebook. A hierarchical voting mechanism sparsely activates personalized interest-agents as fine-grained preference centers. Guided by these agents, Soft-Routing Attention aggregates historical signals in semantic space, weighting by similarity to minimize quantization error and retain long-tail behaviors. Deployed on Taobao's "Guess What You Like" homepage, HiSAC achieves significant compression and cost reduction, with online A/B tests showing a consistent 1.65% CTR uplift -- demonstrating its scalability and real-world effectiveness.

As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an ``all-or-nothing'' approach to memory usage: incorporating all relevant past information can lead to \textit{Memory Anchoring}, where the agent is trapped by past interactions, while excluding memory entirely results in under-utilization and the loss of important interaction history. We show that an agent's reliance on memory can be modeled as an explicit and user-controllable dimension. We first introduce a behavioral metric of memory dependence to quantify the influence of past interactions on current outputs. We then propose \textbf{Stee}rable \textbf{M}emory Agent, \texttt{SteeM}, a framework that allows users to dynamically regulate memory reliance, ranging from a fresh-start mode that promotes innovation to a high-fidelity mode that closely follows interaction history. Experiments across different scenarios demonstrate that our approach consistently outperforms conventional prompting and rigid memory masking strategies, yielding a more nuanced and effective control for personalized human-agent collaboration.

In web environments, user preferences are often refined progressively as users move from browsing broad categories to exploring specific items. However, existing generative recommenders overlook this natural refinement process. Generative recommendation formulates next-item prediction as autoregressive generation over tokenized user histories, where each item is represented as a sequence of discrete tokens. Prior models typically fuse heterogeneous attributes such as ID, category, title, and description into a single embedding before quantization, which flattens the inherent semantic hierarchy of items and fails to capture the gradual evolution of user intent during web interactions. To address this limitation, we propose CoFiRec, a novel generative recommendation framework that explicitly incorporates the Coarse-to-Fine nature of item semantics into the tokenization process. Instead of compressing all attributes into a single latent space, CoFiRec decomposes item information into multiple semantic levels, ranging from high-level categories to detailed descriptions and collaborative filtering signals. Based on this design, we introduce the CoFiRec Tokenizer, which tokenizes each level independently while preserving structural order. During autoregressive decoding, the language model is instructed to generate item tokens from coarse to fine, progressively modeling user intent from general interests to specific item-level interests. Experiments across multiple public benchmarks and backbones demonstrate that CoFiRec outperforms existing methods, offering a new perspective for generative recommendation. Theoretically, we prove that structured tokenization leads to lower dissimilarity between generated and ground truth items, supporting its effectiveness in generative recommendation. Our code is available at https://github.com/YennNing/CoFiRec.

We study Nash equilibrium learning in partially observable Markov games (POMGs), a multi-agent reinforcement learning framework in which agents cannot fully observe the underlying state. Prior work in this setting relies on centralization or information sharing, and suffers from sample and computational complexity that scales exponentially in the number of players. We focus on a subclass of POMGs with independent state transitions, where agents remain coupled through their rewards, and assume that the underlying fully observed Markov game is a Markov potential game. For this class, we present an independent learning algorithm in which players, observing only their own actions and observations and without communication, jointly converge to an approximate Nash equilibrium. Due to partial observability, optimal policies may in general depend on the full action-observation history. Under a filter stability assumption, we show that policies based on finite history windows provide sufficient approximation guarantees. This enables us to approximate the POMG by a surrogate Markov game that is near-potential, leading to quasi-polynomial sample and computational complexity for independent Nash equilibrium learning in the underlying POMG.